Papers with composition functions

2 papers
Unifying Parsing and Tree-Structured Models for Generating Sentence Semantic Representations (2022.naacl-srw)

Copied to clipboard

Challenge: Existing tree-based models require handannotated data to be trained.
Approach: They propose a tree-based model that learns its composition function together with its structure.
Outcome: The proposed model outperforms existing models on downstream tasks and is competitive with Bert base model.
Syntactic Nuclei in Dependency Parsing – A Multilingual Exploration (2021.eacl-main)

Copied to clipboard

Challenge: Existing models for syntactic dependency parsing assume words are elementary units that enter into dependency relations.
Approach: They propose to use composition functions to make a transition-based dependency parser aware of the notion of nucleus.
Outcome: The proposed concept of nucleus gives small but significant improvements in parsing accuracy on 12 languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations